神经网络之文本情感分析（二）

Projet 2

• 在Project 1 中，我们学习了如何处理和统计reviews
• 基于上一个Project”一个萝卜一个坑”的思想，我们将文本进行了数字化，使得文本可以作为输入进行训练
• 在Project 2中我们将构建一个两层的神经网络，并进行训练

import numpy as np
import sys
import time
import pandas as pd

# 读取数据
reviews = pd.read_csv('reviews.txt', header=None)
labels = pd.read_csv('labels.txt', header=None)

构建神经网络

• 构建一个两层的神经网络
• 注意：输入层到隐层不使用任何激活函数，只要隐层到输出层才使用激活函数（为什么这么做？后面的Project会提到）

class SentimentNetwork(object):
    def __init__(self, reviews, labels, hidden_nodes=10, learning_rate = 0.1):
        """
        参数：
            reviews(dataFrame), 用于训练
            labels(dataFrame)， 用于训练
            hidden_nodes(int), 隐层的个数
            learning_rate(double)，学习步长
        """

        np.random.seed(1)

        self.pre_process_data(reviews, labels)

        self.init_network(len(self.review_vocab), hidden_nodes, 1, learning_rate)

    def pre_process_data(self, reviews, labels):
        """
        预处理数据，统计reviews中出现的所有单词，并且生成word2index
        """

        # 统计reviews中出现的所有单词，
        review_vocab = set()
        for review in reviews.values:
            word = review[0].split(' ')
            review_vocab.update(word)

        self.review_vocab = list(review_vocab)

        # 统计labels中所有出现的label(其实在这里，就+1和-1两种)
        label_vocab = set()
        for label in labels.values:
            label_vocab.add(label[0])
        self.label_vocab = list(label_vocab)

        # 构建word2idx，给每个单词安排一个"门牌号"
        self.word2idx = dict()
        for idx, word in enumerate(self.review_vocab):
            self.word2idx[word] = idx

    def init_network(self, input_nodes, hidden_nodes, output_nodes, learning_rate):
        """
        初始化网络的参数
        """
        self.learning_rate = learning_rate
        self.input_nodes = input_nodes
        self.hidden_nodes = hidden_nodes
        self.output_nodes = output_nodes

        self.weights_0_1 = np.random.normal( 0.0, self.input_nodes**-0.5, (self.input_nodes, self.hidden_nodes) )
        self.weights_1_2 = np.random.normal( 0.0, self.hidden_nodes**-0.5, (self.hidden_nodes, self.output_nodes) )

        self.layer_0 = np.zeros((1, self.input_nodes))

    def update_input_layer(self, review):
        """
        对review进行数字化处理，并将结果存放到self.layer_0中，也就是输入层
        """
        self.layer_0 *= 0
        for word in review.split(' '):
            if word.lower() in self.word2idx:
                idx = self.word2idx[word.lower()]
                # 统计单词出现的次数，作为输入
                self.layer_0[0,idx] += 1

    def sigmoid(self, x):
        return 1 / (1 + np.exp(-x))

    def sigmoid_output_2_derivative(self, output):
        return output * (1 - output)

    def get_target_for_label(self,label):
        if label == 'positive':
            return 1
        else:
            return 0

    def train(self, training_reviews, training_label):
        assert(len(training_reviews) == len(training_label))

        correct_so_far = 0

        start = time.time()

        # 进行训练
        for i in range(len(training_reviews)):
            review = training_reviews.iloc[i,0]
            label = training_label.iloc[i,0]

            self.update_input_layer(review)

            layer_1_i = np.dot( self.layer_0, self.weights_0_1 )
            layer_1_o = layer_1_i

            layer_2_i = np.dot( layer_1_o, self.weights_1_2 )
            layer_2_o = self.sigmoid( layer_2_i )

            layer_2_error = layer_2_o - self.get_target_for_label(label)
            layer_2_delta = layer_2_error * self.sigmoid_output_2_derivative(layer_2_o)

            layer_1_error = np.dot( layer_2_delta, self.weights_1_2.T )
            layer_1_delta = layer_1_error
            # 权重更新
            self.weights_1_2 -= np.dot(layer_1_o.T, layer_2_delta) * self.learning_rate
            self.weights_0_1 -= np.dot(self.layer_0.T, layer_1_delta) * self.learning_rate

            if(layer_2_o >= 0.5 and label=='positive'):
                correct_so_far += 1
            elif(layer_2_o < 0.5 and label=='negative'):
                correct_so_far += 1

            elapsed_time = float(time.time() - start)
            reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0

            sys.stdout.write("\rProgress:" + str(100 * i/float(len(training_reviews)))[:4] \
                             + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \
                             + " #Correct:" + str(correct_so_far) + " #Trained:" + str(i+1) \
                             + " Training Accuracy:" + str(correct_so_far * 100 / float(i+1))[:4] + "%")
            if(i % 2500 == 0):
                print("")

    def test(self, testing_reviews, testing_labels):
        assert(len(testing_reviews) == len(testing_labels))

        correct = 0

        start = time.time()

        for i in range(len(testing_reviews)):
            review = testing_reviews.iloc[i,0]
            label = testing_labels.iloc[i,0]

            pred = self.run(review)
            if pred == label:
                correct += 1

            elapsed_time = float(time.time() - start)
            reviews_per_second = i / elapsed_time if elapsed_time > 0 else 0

            sys.stdout.write("\rProgress:" + str(100 * i/float(len(testing_reviews)))[:4] \
                             + "% Speed(reviews/sec):" + str(reviews_per_second)[0:5] \
                             + " #Correct:" + str(correct) + " #Tested:" + str(i+1) \
                             + " Testing Accuracy:" + str(correct * 100 / float(i+1))[:4] + "%")


    def run(self, review):
        self.update_input_layer(review)

        layer_1_i = np.dot( self.layer_0, self.weights_0_1 )
        layer_1_o = layer_1_i

        layer_2_i = np.dot( layer_1_o, self.weights_1_2 )
        layer_2_o = self.sigmoid( layer_2_i )            
        if layer_2_o >= 0.5:
            return 'positive'
        else:
            return 'negative'

mlp = SentimentNetwork(reviews, labels)

mlp.train(reviews[:-1000], labels[:-1000])

Progress:0.0% Speed(reviews/sec):0 #Correct:0 #Trained:1 Training Accuracy:0.0%
Progress:10.4% Speed(reviews/sec):101.5 #Correct:1246 #Trained:2501 Training Accuracy:49.8%
Progress:20.8% Speed(reviews/sec):103.1 #Correct:2496 #Trained:5001 Training Accuracy:49.9%
Progress:31.2% Speed(reviews/sec):103.4 #Correct:3746 #Trained:7501 Training Accuracy:49.9%
Progress:41.6% Speed(reviews/sec):101.3 #Correct:4996 #Trained:10001 Training Accuracy:49.9%
Progress:52.0% Speed(reviews/sec):99.30 #Correct:6246 #Trained:12501 Training Accuracy:49.9%
Progress:62.5% Speed(reviews/sec):98.82 #Correct:7496 #Trained:15001 Training Accuracy:49.9%
Progress:72.9% Speed(reviews/sec):98.57 #Correct:8746 #Trained:17501 Training Accuracy:49.9%
Progress:83.3% Speed(reviews/sec):98.86 #Correct:9996 #Trained:20001 Training Accuracy:49.9%
Progress:93.7% Speed(reviews/sec):99.27 #Correct:11246 #Trained:22501 Training Accuracy:49.9%
Progress:99.9% Speed(reviews/sec):99.44 #Correct:11995 #Trained:24000 Training Accuracy:49.9%

• 从输出的训练信息来看，始终在50%徘徊，也就是说根本没有进展，对于这种情况，我们首先要做的就是试一试调小learning_rate

mlp = SentimentNetwork(reviews, labels, learning_rate=0.01)

mlp.train(reviews[:-1000], labels[:-1000])

Progress:0.0% Speed(reviews/sec):0.0 #Correct:0 #Trained:1 Training Accuracy:0.0%
Progress:10.4% Speed(reviews/sec):103.6 #Correct:1329 #Trained:2501 Training Accuracy:53.1%
Progress:20.8% Speed(reviews/sec):103.5 #Correct:2923 #Trained:5001 Training Accuracy:58.4%
Progress:31.2% Speed(reviews/sec):99.96 #Correct:4593 #Trained:7501 Training Accuracy:61.2%
Progress:41.6% Speed(reviews/sec):97.92 #Correct:6341 #Trained:10001 Training Accuracy:63.4%
Progress:52.0% Speed(reviews/sec):97.22 #Correct:8105 #Trained:12501 Training Accuracy:64.8%
Progress:62.5% Speed(reviews/sec):97.64 #Correct:9889 #Trained:15001 Training Accuracy:65.9%
Progress:72.9% Speed(reviews/sec):97.91 #Correct:11671 #Trained:17501 Training Accuracy:66.6%
Progress:83.3% Speed(reviews/sec):97.92 #Correct:13530 #Trained:20001 Training Accuracy:67.6%
Progress:93.7% Speed(reviews/sec):97.92 #Correct:15384 #Trained:22501 Training Accuracy:68.3%
Progress:99.9% Speed(reviews/sec):97.82 #Correct:16531 #Trained:24000 Training Accuracy:68.8%

mlp.test(reviews[-1000:], labels[-1000:])

Progress:99.9% Speed(reviews/sec):861.2 #Correct:747 #Tested:1000 Testing Accuracy:74.7%

End Project 2

• 通过训练，我们的神经网络能达到60%以上的准确率，至少比猜的结果要好，不错，这是一个好的开始。
• 准确率只有70多，可提升的空间还有很大，在下一个Project，我们将进行分析如何提高准确率